École normale supérieure de Cachan

About: École normale supérieure de Cachan is a education organization based out in Cachan, Île-de-France, France. It is known for research contribution in the topics: Decidability & Nonlinear system. The organization has 2717 authors who have published 5585 publications receiving 175925 citations.

Productivity, relationship-specific inputs and the sourcing modes of multinationals

Abstract: We investigate the roles of productivity and the specificity of inputs for the international sourcing strategy of firms which are part of a multinational network. We present a framework in which firms decide to import from a foreign independent supplier or from their related party abroad according to these two dimensions. We use a detailed survey that provides a detailed geographical breakdown of French firms’ imports at the product level as well as the sourcing mode used for each transaction. The dataset also provides information to estimate the firms’ productivity and their intensity in relationship-specific inputs. After controlling for countries of origin, products and sectors specific effects, the empirical results provide evidence that for the most productive multinationals the likelihood of trading through an independent supplier is higher especially if they use relationship-specific inputs intensively.

Tree-Based Ranking Methods

Abstract: This paper investigates how recursive partitioning methods can be adapted to the bipartite ranking problem. In ranking, the pursued goal is global: based on past data, define an order on the whole input space X, so that positive instances take up the top ranks with maximum probability. The most natural way to order all instances consists of projecting the input data onto the real line through a real-valued scoring function s and use the natural order on R. The accuracy of the ordering induced by a candidate s is classically measured in terms of the ROC curve or the AUC. Here we discuss the design of tree-structured scoring functions obtained by recursively maximizing the AUC criterion. The connection with recursive piecewise linear approximation of the optimal ROC curve both in the L1-sense and in the Linfin-sense is highlighted. A novel tree-based algorithm for ranking, called TreeRank, is proposed. Consistency results and generalization bounds of functional nature are established for this ranking method, when considering either the L1 or Linfin distance. We also describe committee-based learning procedures using TreeRank as a ldquobase ranker,rdquo in order to overcome obvious drawbacks of such a top-down partitioning technique. Simulation results on artificial data are also displayed.